Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shennawardana23/skillme --skill orchestratorgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shennawardana23/skillme/orchestrator)<a href="https://agentmods.dev/skills/shennawardana23/skillme/orchestrator"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shennawardana23/skillme/orchestrator"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00107 | $0.01333 |
| Opus 5 | $0.00053 | $0.00666 |
| Sonnet 5 | $0.00021 | $0.00267 |
| Haiku 4.5 | $0.00011 | $0.00133 |
Grade A, and why
orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator
A routing discipline for picking which skill in a catalog actually applies to an incoming request, and for handling requests that span more than one. The core failure this prevents: improvising a generic answer because the exact matching skill wasn't obviously the top hit, when a specific skill with real domain knowledge exists and should be loaded and followed instead.
Build a routing table, don't route from memory
Maintain an explicit table of task signal to skill, and consult it before answering — don't rely on recalling what skills exist from general impression. A table survives catalog growth; memory doesn't.
| Signal in the request | Route to | Example phrasing |
|---|---|---|
| "is this correct", a diff, a PR to review | your code-review skill | "review this PR", "is this a good change" |
| "is this secure", auth/input-handling changes | your security-review skill | "check for vulnerabilities", "is this safe to expose" |
| A schema change, a new table, partitioned tables | your database-migration skill | "add a column", "migrate this table" |
| "implement", "build", "add feature" | your feature-implementation / TDD skill | "add support for X" |
| "write tests", "add coverage" | your test-driven-development or e2e-testing skill | "test this", "add E2E coverage" |
| An error message, a stack trace | your debugging skill | "why is this failing" |
| Go-specific idiom questions | your go-service-idioms skill | "is this idiomatic Go" |
| Framework-specific UI questions (Vue/Nuxt, Laravel) | your framework-pattern skill | "how should this component be structured" |
| A request spanning code generation and review | your agentic-engineering / ai-first-engineering skills | "decompose this for an agent", "what should the review focus on" |
Adapt the right-hand column to your catalog's actual skill names — the point is the shape of the table (a signal maps to exactly one primary skill), not these specific entries.
Process
- Identify the task type from the signals in the request, using the table above — not from a first impression of what the request "feels like."
- Load the matched skill in full and follow its instructions as written. Don't improvise a plausible-sounding process instead of reading the actual skill — the whole point of having a skill catalog is that the specific skill encodes domain knowledge a generic response won't reproduce.
- For multi-step tasks, follow the skill's own phase structure in the order it specifies, rather than reordering steps because a different order seems more natural.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 112 lines · 107 tokens per session scan A f550d260422f
orchestrator is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,333 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
php-pro
A set of practices for building PHP applications with modern PHP, Laravel, or Symfony. PHP is a programming language commonly used for server-side web applications.
mvc-expert
Expert guidelines to refactor legacy PHP codebases into clean, modern, and scalable MVC-structured projects / Pedoman ahli untuk merefaktor codebase PHP lama menjadi proyek terstruktur MVC yang bersih, modern, dan skalabel.
bd-better-route-bridge
Compose better-data DTOs with the better-route library — use BetterRouteBridge::{get, post, put, patch, delete} to register a REST route that hydrates the request into a DTO, validates, calls the handler with (DataObject, mixed $request), and presents returned DataObject values through Presenter with…
bd-data-object
Add or modify DataObject subclasses inside the better-data library — the immutable, attribute-decorated DTOs the whole library is built around. Every DTO is final readonly class extends DataObject with constructor-promoted typed parameters; sources hydrate via ::fromArray, sinks project via SinkProjection, the…
wp-plugin-bootstrap
Scaffolds and reviews the main entry-point PHP file of a WordPress plugin — header (with Requires Plugins for WP 6.5+), ABSPATH guard, file/path/url/version constants, Composer PSR-4 autoload with src/ as the default class root, optional scoped fallback for release ZIP safety, PascalCase class filenames that match…
bd-hydration-coercion
Modify how raw values become typed property values in better-data — work in TypeCoercer (primitives + DateTime + Enum + Secret) or DataObject::coerceParameter (attribute-aware — ListOf, Encrypted, etc.). Critical layering — TypeCoercer is pure, must stay callable from a no-WordPress unit test, no side effects, no…